scofield7419/StruMatchDL
Codes for ICML 2022 paper: Matching Structure for Dual Learning
This project improves natural language processing (NLP) tasks that involve translating or transforming text, or converting between text and non-text formats like images. It takes raw text inputs (like English sentences for translation) and uses their underlying grammatical structure to produce more accurate and contextually relevant outputs. This tool is for researchers and advanced practitioners in NLP who need to build or enhance systems for tasks like machine translation or text summarization.
No commits in the last 6 months.
Use this if you are working on dual learning NLP tasks, such as translating between two languages or converting text to a database query and back, and want to improve accuracy by incorporating the grammatical and semantic structure of the input data.
Not ideal if your NLP tasks don't involve a 'dual' relationship (e.g., text-to-text or text-to-non-text transformations), or if you are not comfortable with advanced machine learning research frameworks.
Stars
12
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/scofield7419/StruMatchDL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification